Triple

T30166491
Position Surface form Disambiguated ID Type / Status
Subject Вознесенский проспект E766805 entity
Predicate расположение P25921 FINISHED
Object центр Санкт-Петербурга LITERAL FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: центр Санкт-Петербурга | Statement: [Вознесенский проспект, расположение, центр Санкт-Петербурга]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: расположение
Context triple: [Вознесенский проспект, расположение, центр Санкт-Петербурга]
  • A. propertyLocation chosen
    Indicates the geographical place or address where a property is situated or found.
  • B. расположенаНа
    Indicates that one entity is located on the surface or area of another entity.
  • C. locates
    Indicates that one entity determines, specifies, or identifies the position or place of another entity in space or within a given context.
  • D. luogo
    Indicates that something is located, occurs, or exists in a particular place or location.
  • E. locatedAlong
    Indicates that one entity is situated adjacent to, or running beside, the length or course of another linear feature (such as a road, river, or railway).
  • F. None of above.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69f2247a968881909d79c18f2bfcb275 completed April 29, 2026, 3:32 p.m.
NER Named-entity recognition batch_69f67f073dbc8190a42f4c71ad2f7de3 completed May 2, 2026, 10:47 p.m.
PD Predicate disambiguation batch_69f673c7a4588190837854f3ef61e6bf completed May 2, 2026, 9:59 p.m.
Created at: April 29, 2026, 7:23 p.m.